Identification of key biomarkers for early warning of diabetic retinopathy using BP neural network algorithm and hierarchical clustering analysis.

Diabetic retinopathy is one of the most common microangiopathy in diabetes, essentially caused by abnormal blood glucose metabolism resulting from insufficient insulin secretion or reduced insulin activity. Epidemiological survey results show that about one third of diabetes patients have signs of diabetic retinopathy, and another third may suffer from serious retinopathy that threatens vision. However, the pathogenesis of diabetic retinopathy is still unclear, and there is no systematic method to detect the onset of the disease and effectively predict its occurrence. In this study, we used medical detection data from diabetic retinopathy patients to determine key biomarkers that induce disease onset through back propagation neural network algorithm and hierarchical clustering analysis, ultimately obtaining early warning signals of the disease. The key markers that induce diabetic retinopathy have been detected, which can also be used to explore the induction mechanism of disease occurrence and deliver strong warning signal before disease occurrence. We found that multiple clinical indicators that form key markers, such as glycated hemoglobin, serum uric acid, alanine aminotransferase are closely related to the occurrence of the disease. They respectively induced disease from the aspects of the individual lipid metabolism, cell oxidation reduction, bone metabolism and bone resorption and cell function of blood coagulation. The key markers that induce diabetic retinopathy complications do not act independently, but form a complete module to coordinate and work together before the onset of the disease, and transmit a strong warning signal. The key markers detected by this algorithm are more sensitive and effective in the early warning of disease. Hence, a new method related to key markers is proposed for the study of diabetic microvascular lesions. In clinical prediction and diagnosis, doctors can use key markers to give early warning of individual diseases and make early intervention.

Nothing means anything if everything means something: exploring the issues of coping profiles and the person-centered approach.

BACKGROUND: Adopting a person-centered approach to coping potentially allows researchers to explore the multifaceted nature of the construct. However, this increasingly adopted approach also has limitations. Namely, employing cluster or latent profile analysis to investigate coping through a person-centered lens often brings a lack of generalizability and subjectivity in interpreting the generated profiles. As such, this study aimed to explore the impact of varied methodology in person-centered investigations of coping profiles. METHODS: 682 university students' (M = 21.3 years old, SD = 3.5) responses to the COPE Inventory were analyzed across item, subscale, and higher-order category levels using cluster and latent profile analysis to produce 6 finalized models for cross-method comparison. RESULTS: Throughout 19 analyses, approach coping, avoidance coping, low coping, and help-seeking profiles were consistently identified, alluding to the potential of universal coping trends. However, membership overlap across COPE structures and methodology was largely inconsistent, with individual participants classified into theoretically distinct profiles based on the methodology employed. CONCLUSION: While evidence suggests latent profile analysis provides a more rigorous approach, the significant impact of minor methodological variations urges a reevaluation of person-centered approaches and incorporation of multi-construct data to enhance the understanding of coping profiles.

Fire protection priorities in the oak forests of Iran with an emphasis on vertebrate habitat preservation.

This study examines the impact of fire incidents on wildlife and habitats in the western oak forests of Iran (Zagros region). These forests are globally recognized for their exceptional biodiversity but are frequently threatened by wildfires. To achieve this, the study uses the space-time scan statistics permutation (STSSP) model to identify areas with a higher frequency of fires. The study also analyzes the effects of fires on the Zagros forests from 2000 to 2021 using remote-sensing MODIS data. Also, to understand the elements at risk of fire, burned areas were assessed based on the richness of vertebrate species, determined by the distribution of 88 vertebrate species. The results show that the annual fire rate in the Zagros forests is 76.2 (fire occurrences per year), calculated using the Poisson distribution. Findings show the highest fire rates are found in the northwest and a part of the south of the Zagros. The northwest of the Zagros also has the largest number of single fires and clusters, indicating a wide spatial distribution of fire in these regions. On the other side, it was unexpectedly found that these regions have the richest number of species and higher habitat value. The results demonstrate a significant correlation between the value of the habitat and the extent of burned areas (p < 0.05). The study also reveals that the greatest impact of fires is on small vertebrates. The overlap of frequent fire spots with the richest regions of Zagros oak forests in terms of vertebrate diversity emphasizes the need for strategic forest risk reduction planning, especially in these priority zones.

Research on the relation between hydro-chemical and geological characteristics in karst area: Case study in Zhong Liang Mountain, Southwest China.

Karst groundwater, which is one of most important drinking water sources, is vulnerable to be polluted as its closed hydraulic relation with surface water. Thus, it is very important to identify the groundwater source to control groundwater pollution. The Pearson correlation coefficient among major ions (Na + K+, Ca2+, Mg2+, HCO3 -, SO4 2-, and Cl-) was employed to deduce the groundwater types in Zhong Liang Mountain, Southwest China. Then, the combined method of principal component analysis and cluster analysis were employed to identify the groundwater sources in a typical karst region of southwest China. The results shown that (1) the high positive correlation between cations and anions indicated the water-rock reaction of Ca-HCO3, Ca-SO4, (Na + K)-Cl, and Mg-SO4. (2) The major two principal components that would represent water-rock reaction of CaSO4 and Ca-HCO3 would, respectively, explain 60.41% and 31.80% of groundwater information. (3) Based on the two principal components, 33 groundwater samples were clustered into eight groups through hierarchical clustering, each group has similar water-rock reaction. The findings would be employed to forecast the surge water, that was an important work for tunnel construction and operation. PRACTITIONER POINTS: The components of groundwater was highly correlated with water-rock reaction. The principal component analysis screens the types of groundwater. The cluster analysis identifies the groundwater sources.

Integration of two-dimensional echocardiography: A novel risk indicator for ST-segment elevation myocardial infarction.

AIMS: We aim to integrate the parameters of two-dimensional (2D) echocardiography and identify the high-risk population for all-cause mortality in patients with acute ST-segment elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI). METHODS: The study involved a retrospective cohort population with STEMI who were admitted to Yongchuan Hospital of Chongqing Medical University between January 2016 and January 2019. Baseline data were collected, including 2D echocardiography parameters and left ventricular ejection fraction (LVEF). The parameters of 2D echocardiography were subjected to cluster analysis. Logistic regression models were employed to assess univariate and multivariate adjusted odds ratios (ORs) of cluster information in relation to all-cause mortality. Four logistic regression models were generated, utilizing cluster information, clinical variables, clinical variables in conjunction with LVEF, and clinical variables in conjunction with LVEF and cluster information as predictive variables, respectively. The area under the curve (AUC) were utilized to evaluate the incremental risk stratification value of cluster information. RESULTS: The study included 633 participants with 28.8% female, a mean age of 65.68 ± 11.98 years. Over the course of a 3-year follow-up period, 108 (17.1%) patients experienced all-cause mortality. Utilizing cluster analysis of 2D echocardiography parameters, the patients were categorized into two distinct clusters, with statistically significant differences observed in most clinical variables, echocardiography, and survival outcomes between the clusters. Multivariate regression analysis revealed that cluster information was independently associated with the risk of all-cause mortality with adjusted OR 7.33 (95% confidence interval [CI] 3.99-14.06, P < 0.001). The inclusion of LVEF enhanced the predictive capacity of the model utilized with clinical variables with AUC 0.848 (95% CI 0.809-0.888) versus AUC 0.872 (95% CI 0.836-0.908) (P < 0.001), and the addition of cluster information further improved its predictive performance with AUC 0.906 (95% CI 0.878-0.934, P < 0.001). This cluster analysis was translated into a free available online calculator (https://app-for-mortality-prediction-cluster.streamlit.app/). CONCLUSIONS: The 2D echocardiographic diagnostic information based on cluster analysis had good prognostic value for STEMI population, which was helpful for risk stratification and individualized intervention.

Phenotyping variability in early socio-communicative skills in young children with autism and its influence on later development.

Children with autism spectrum disorder (ASD) often face challenges in early social communication skills, prompting the need for a detailed exploration of specific behaviors and their impact on cognitive and adaptive functioning. This study aims to address this gap by examining the developmental trajectories of early social communication skills in preschoolers with ASD aged 18-60 months, comparing them to age-matched typically developing (TD) children. Utilizing the early social communication scales (ESCS), the research employs a longitudinal design to capture changes over time. We apply a principal component analysis (PCA) to ESCS variables to identify underlying components, and cluster analysis to identify subgroups based on preverbal communication profiles. The results reveal consistent differences in early social communication skills between ASD and TD children, with ASD children exhibiting reduced skills. PCA identifies two components, distinguishing objects-directed behaviors and social interaction-directed behaviors. Cluster analysis identifies three subgroups of autistic children, each displaying specific communication profiles associated with distinct cognitive and adaptive functioning trajectories. In conclusion, this study provides a nuanced understanding of early social communication development in ASD, emphasizing the importance of low-level behaviors. The identification of subgroups and their unique trajectories contributes to a more comprehensive understanding of ASD heterogeneity. These findings underscore the significance of early diagnosis, focusing on specific behaviors predicting cognitive and adaptive functioning outcomes. The study encourages further research to explore the sequential development of these skills, offering valuable insights for interventions and support strategies.

Exploring the influence of slaughterhouse type and slaughtering steps on Campylobacter jejuni contamination in chicken meat: A cluster analysis approach.

Campylobacter jejuni (C. jejuni), a foodborne pathogen, poses notable hazards to human health and has significant economic implications for poultry production. This study aimed to assess C. jejuni contamination levels in chicken carcasses from both backyard and commercial slaughterhouses in Chiang Mai province, Thailand. It also sought to examine the effects of different slaughtering practices on contamination levels and to offer evidence-based recommendations for reducing C. jejuni contamination. Through the sampling of 105 chicken carcasses and subsequent enumeration of C. jejuni, the study captured the impact of various slaughtering practices. Utilizing k-modes clustering on the observational and bacterial count data, the research identified distinct patterns of contamination, revealing higher levels in backyard operations compared to commercial ones. The application of k-modes clustering highlighted the impact of critical slaughtering practices, particularly chilling, on contamination levels. Notably, samples with the lowest bacterial counts were typically from the chilling step, a practice predominantly found in commercial facilities. This observation underpins the recommendation for backyard slaughterhouses to incorporate ice in their post-evisceration soaking process. Mimicking commercial practices, this chilling method aims to inhibit C. jejuni growth by reducing carcass temperature, thereby enhancing food safety. Furthermore, the study suggests backyard operations adopt additional measures observed in commercial settings, like segregating equipment for each slaughtering step and implementing regular cleaning protocols. These strategic interventions are pivotal in reducing contamination risks, advancing microbiological safety in poultry processing, and aligning with global food safety enhancement efforts.

Measuring the Scientific Impact of Growth Hormone Treatment in Burns: A Bibliometric Analysis Based on CiteSpace.

This study utilized CiteSpace software to conduct a bibliometric analysis of the literature related to the use of growth hormone in treating burns. The results showed that the research on this topic has attracted increasing attention from scholars worldwide, with the number of publications increasing annually. The research teams and institutions involved in this field are mainly concentrated in China, followed by the United States, Russia, and other countries. The analysis also revealed the prominent co-cited literature and the most influential authors in the field, such as Herndon，DN.and Li Y. The main research themes identified in the literature included the effects of growth hormone on wound healing, tissue repair and regeneration, inflammatory responses, and cell proliferation. Additionally, the research on the clinical applications of growth hormone in burn treatment has been expanded to include areas such as metabolic regulation, immune function, and the prevention of infections. The findings of this study provide useful insights into the current status and future directions of research in the field of growth hormone treatment of burns.

Phenotypic subgroup in serologically active clinically quiescent systemic lupus erythematosus: A cluster analysis based on CSTAR cohort.

BACKGROUND: Serologically active clinically quiescent (SACQ) is a state within systemic lupus erythematosus (SLE) characterized by elevated serologic markers without clinical activity. The heterogeneity in SACQ patients poses challenges in disease management. This multicenter prospective study aimed to identify distinct SACQ subgroups and assess their utility in predicting organ damage. METHODS: SACQ was defined as a sustained period of at least 6 months with persistent serologic activity, marked by positive anti-double-stranded DNA (dsDNA) antibodies and/or hypocomplementemia, and without clinical activity. Cluster analysis was employed, utilizing 16 independent components to delineate phenotypes. FINDINGS: Among the 4,107 patients with SLE, 990 (24.1%) achieved SACQ within 2.0 ± 2.3 years on average. Over a total follow-up of 7,105.1 patient years, 340 (34.3%) experienced flares, and 134 (13.5%) developed organ damage. Three distinct SACQ subgroups were identified. Cluster 1 (n = 219, 22.1%) consisted predominantly of elderly males with a history of major organ involvement at SLE diagnosis, showing the highest risk of severe flares (16.4%) and organ damage (27.9%). Cluster 2 (n = 279, 28.2%) was characterized by milder disease and a lower risk of damage accrual (5.7%). Notably, 86 patients (30.8%) in cluster 2 successfully discontinued low-dose glucocorticoids, with 49 of them doing so without experiencing flares. Cluster 3 (n = 492, 49.7%) featured the highest proportion of lupus nephritis and a moderate risk of organ damage (11.8%), with male patients showing significantly higher risk of damage (hazard ratio [HR] = 4.51, 95% confidence interval [CI], 1.82-11.79). CONCLUSION: This study identified three distinct SACQ clusters, each with specific prognostic implications. This classification could enhance personalized management for SACQ patients. FUNDING: This work was funded by the National Key R&D Program (2021YFC2501300), the Beijing Municipal Science & Technology Commission (Z201100005520023), the CAMS Innovation Fund (2021-I2M-1-005), and National High-Level Hospital Clinical Research Funding (2022-PUMCH-D-009).

Omada: robust clustering of transcriptomes through multiple testing.

BACKGROUND: Cohort studies increasingly collect biosamples for molecular profiling and are observing molecular heterogeneity. High-throughput RNA sequencing is providing large datasets capable of reflecting disease mechanisms. Clustering approaches have produced a number of tools to help dissect complex heterogeneous datasets, but selecting the appropriate method and parameters to perform exploratory clustering analysis of transcriptomic data requires deep understanding of machine learning and extensive computational experimentation. Tools that assist with such decisions without prior field knowledge are nonexistent. To address this, we have developed Omada, a suite of tools aiming to automate these processes and make robust unsupervised clustering of transcriptomic data more accessible through automated machine learning-based functions. FINDINGS: The efficiency of each tool was tested with 7 datasets characterized by different expression signal strengths to capture a wide spectrum of RNA expression datasets. Our toolkit's decisions reflected the real number of stable partitions in datasets where the subgroups are discernible. Within datasets with less clear biological distinctions, our tools either formed stable subgroups with different expression profiles and robust clinical associations or revealed signs of problematic data such as biased measurements. CONCLUSIONS: In conclusion, Omada successfully automates the robust unsupervised clustering of transcriptomic data, making advanced analysis accessible and reliable even for those without extensive machine learning expertise. Implementation of Omada is available at http://bioconductor.org/packages/omada/.

A new classification for emergency critically ill patients and analysis of their adverse events during intrahospital transport: A cluster analysis.

BACKGROUND: Critical patients may experience various adverse events during transportation within hospitals. Therefore, quickly evaluating and classifying patients before transporting them from the emergency department and focusing on managing high-risk patients are critical. At present, no unified classification method exists; all the current approaches are subjective. AIMS: To ensure transportation safety, we conducted a cluster analysis of critically ill patients transferred from the emergency department to the intensive care unit. STUDY DESIGN: Single-centre cohort study. This study was conducted at a comprehensive first-class teaching hospital in Beijing. Convenience sampling and continuous enrolment were employed. We collected data from 1 January 2019, to 31 December 2021. All patients were transferred from the emergency department to the intensive care unit, and cluster analysis was conducted using five variables. RESULTS: A total of 584 patients were grouped into three clusters. Cluster 1 (high systolic blood pressure group) included 208 (35.6%) patients. Cluster 2 (high heart rate and low blood oxygen group) included 55 (9.4%) patients. Cluster 3 (normal group) included the remaining 321 (55%) patients. The oxygen saturation levels of all the patients were lower after transport, and the proportion of adverse events (61.8%) was the highest in Cluster 2 (p < .05). CONCLUSIONS: This study utilized data on five important vital signs from a cluster analysis to explore possible patient classifications and provide a reference for ensuring transportation safety. RELEVANCE TO CLINICAL PRACTICE: Before transferring patients, we should classify them and implement targeted care. Changes in blood oxygen levels in all patients should be considered, with a focus on the occurrence of adverse events during transportation among patients with high heart rates and low blood oxygen levels.

Machine learning-based cluster analysis identifies four unique phenotypes of patients with degenerative cervical myelopathy with distinct clinical profiles and long-term functional and neurological outcomes.

BACKGROUND: Degenerative cervical myelopathy (DCM), the predominant cause of spinal cord dysfunction among adults, exhibits diverse interrelated symptoms and significant heterogeneity in clinical presentation. This study sought to use machine learning-based clustering algorithms to identify distinct patient clinical profiles and functional trajectories following surgical intervention. METHODS: In this study, we applied k-means and latent profile analysis (LPA) to identify patient phenotypes, using aggregated data from three major DCM trials. The combination of Nurick score, NDI (neck disability index), neck pain, as well as motor and sensory scores facilitated clustering. Goodness-of-fit indices were used to determine the optimal cluster number. ANOVA and post hoc Tukey's test assessed outcome differences, while multinomial logistic regression identified significant predictors of group membership. FINDINGS: A total of 1047 patients with DCM (mean [SD] age: 56.80 [11.39] years, 411 [39%] females) had complete one year outcome assessment post-surgery. Latent profile analysis identified four DCM phenotypes: "severe multimodal impairment" (n = 286), "minimal impairment" (n = 116), "motor-dominant" (n = 88) and "pain-dominant" (n = 557) groups. Each phenotype exhibited a unique symptom profile and distinct functional recovery trajectories. The "severe multimodal impairment group", comprising frail elderly patients, demonstrated the worst overall outcomes at one year (SF-36 PCS mean [SD]: 40.01 [9.75]; SF-36 MCS mean [SD], 46.08 [11.50]) but experienced substantial neurological recovery post-surgery (ΔmJOA mean [SD]: 3.83 [2.98]). Applying the k-means algorithm yielded a similar four-class solution. A higher frailty score and positive smoking status predicted membership in the "severe multimodal impairment" group (OR 1.47 [95% CI 1.07-2.02] and 1.58 [95% CI 1.25-1.99, respectively]), while undergoing anterior surgery and a longer symptom duration were associated with the "pain-dominant" group (OR 2.0 [95% CI 1.06-3.80] and 3.1 [95% CI 1.38-6.89], respectively). INTERPRETATION: Unsupervised learning on multiple clinical metrics predicted distinct patient phenotypes. Symptom clustering offers a valuable framework to identify DCM subpopulations, surpassing single patient reported outcome measures like the mJOA. FUNDING: No funding was received for the present work. The original studies were funded by AO Spine North America.

Assessing the impact of history of medicine research: A scientometric and altmetric analysis.

Background and Aims: After conducting a comprehensive literature search of two medical electronic databases, PubMed and Embase, as well as two citation databases, Web of Science Core Collections (WoS) and Scopus, we aimed to conduct an Altmetric and Scientometric analysis of the History of Medicine literature in medical research. Methods: The following software tools were used for analyzing the retrieved records from PubMed and Embase databases and conducting a collaboration analysis to identify the countries involved in scientific medical papers, as well as clustering keywords to reveal the trend of History of Medicine research for the future. These software tools (VOSviewer 1.6.18 and Spss 16) allowed the researchers to visualize bibliometric networks, perform statistical analysis, and identify patterns and trends in the data. Results: Our analysis revealed 53,771 records from PubMed and 54,405 records from EMBASE databases retrieved in the field of History of Medicine by 105,286 contributed authors in WoS. We identified 157 countries that collaborated on scientific medical papers. By clustering 59,995 keywords, we were able to reveal the trend of History of Medicine research for the future. Our findings showed a positive association between traditional bibliometrics and social media metrics such as the Altmetric Attention Score in the History of Medicine literature (p < 0.05). Conclusion: Sharing research findings of articles in social scientific networks will increase the visibility of scientific works in History of Medicine research, which is one of the most important factors influencing the citation of articles. Additionally, our overview of the literature in the medical field allowed us to identify and examine gaps in the History of Medicine research.

Cluster analysis of clinical manifestations assigns systemic lupus erythematosus-phenotype subgroups: a multicentre study on 440 patients.

OBJECTIVE: Systemic lupus erythematous (SLE) is a heterogenous disease characterised by a large panel of autoantibodies and a wide spectrum of clinical signs and symptoms that engender different outcomes. We aimed to identify distinct, homogeneous SLE patients' phenotypes. METHODS: This retrospective study enrolled SLE patients meeting the Systemic Lupus International Collaborating Clinics (SLICC) classification criteria, enrolled in the French multicentre "APS (antiphospholipid syndrome) and SLE‿ Registry. Based on 29 variables selected to cover a broad range of clinical and laboratory (excluding autoantibodies) SLE manifestations, unsupervised multiple correspondence analysis followed by hierarchical ascendent-clustering analysis assigned different phenotypes. RESULTS: We included 440 patients, mostly women (94.3%). Median age at SLE diagnosis was 24 (IQR 19-32) years. Cluster analysis yielded three distinct subgroups based on cumulative clinical manifestations, not autoantibody pattern. Cluster 1 (n=91) comprised mostly Caucasian patients, with APS-associated clinical and biological manifestations, e.g., livedo, seizure, thrombocytopaenia and haemolytic anaemia. Cluster 2 (n=221), the largest, included patients with mild clinical manifestations, mainly articular, more frequently associated with Sjögren's syndrome and with less frequent autoantibody-positivity. Cluster 3 (n=128) consisted of patients with the largest panel of SLE-specific clinical manifestations (cutaneous, articular, proliferative nephritis, pleural, cardiac and haematological), the most frequent autoantibody-positivity, low complement levels, and more often of Asian and sub-Saharan African origin. CONCLUSION: This unsupervised clustering method distinguished three distinct SLE patient subgroups, highlighting SLE heterogeneity.

Identifying Variation in Physical Health Behaviors and Depressive Symptoms among Religiosity Clusters of African American Adults in the United States.

Religiosity is an important factor in the lives of many African Americans, who suffer a greater health burden than their White counterparts. In this study, we examined associations between dimensions of religiosity with health behaviors and depressive symptoms in a sample of African American adults in the United States. Participants (N = 2086) completed five measures of religiosity (religious involvement, positive and negative religious coping, scriptural influence, belief in illness as punishment for sin) and measures of several health behaviors, cancer screening behaviors, and depressive symptoms. Using cluster analysis to examine the deep structure of religiosity, three clusters emerged: Positive Religious, Negative Religious, and Low Religious. In general, the Positive Religious group engaged in more healthy behaviors (e.g., fruit and vegetable consumption, fecal occult blood test) and fewer risky health behaviors (e.g., smoke and consume alcohol), and reported fewer depressive symptoms than did the Negative Religious and/or Low Religious groups. Theoretical implications and implications for interventions by clergy and mental health professionals are discussed.

Unsupervised Clustering Analysis of Regimen and HLA Characteristics in Pediatric Umbilical Cord Blood Transplantation.

BACKGROUND: Human leukocyte antigen (HLA) matching is a critical factor in allogeneic unrelated hematopoietic cell transplantation (HCT) due to its impact on post-transplant survival and quality of life. Umbilical cord blood transplantation (UCBT) offers unique advantages but the optimal approach to graft selection and immunosuppression remains challenging. Unsupervised clustering, a machine learning technique has potential in analyzing transplant outcomes but its application in investigating leukemia outcomes has been limited. OBJECTIVE: To identify optimal combinations of HLA/KIR donor-patient pairing, conditioning, and immunosuppressive regimens in pediatric patients with acute lymphoblastic (ALL) or acute myeloblastic (AML) leukemia undergoing umbilical cord blood transplantation (UCBT). STUDY DESIGN: Outcome data for single, unmanipulated UCBT in pediatric AML (n=708) and ALL (n=1034) patients from the Eurocord/EBMT registry were analyzed using unsupervised clustering. Resulting clusters were used to inform post-hoc competing risks and Kaplan-Meier analyses. RESULTS: In AML, single HLA-C mismatches with other loci fully matched (7/8) associated with poorer relapse-free survival (RFS) (p=0.039), but a second mismatch at any other locus counteracted this effect. In ALL, total body irradiation (TBI) effectively prevented relapse mortality (p=0.007). KIR/HLA-C match status affected RFS in AML (p=0.039) but not ALL (p=0.8). Anti-thymocyte globulin (ATG) administration substantially increased relapse, with no relapses occurring in the 85 patients not receiving ATG. CONCLUSIONS: Our unsupervised clustering analyses generate several key statistical and mechanistic hypotheses regarding the relationships between HLA matching, conditioning regimens, immunosuppressive therapies, and transplantation outcomes in pediatric AML and ALL patients. HLA-C and killer immunoglobulin receptor (KIR) combinations significantly impact RFS in pediatric AML, but not ALL. ATG use in fully matched pediatric patients is associated with late-stage relapse. TBI regimens appear beneficial in ALL, with efficacy largely independent of histocompatibility variables. These findings reflect the distinct genetic and biological profiles of AML and ALL.

Consistency is key: documentation distribution and efficiency in primary care.

OBJECTIVES: We analyzed the degree to which daily documentation patterns in primary care varied and whether specific patterns, consistency over time, and deviations from clinicians' usual patterns were associated with note-writing efficiency. MATERIALS AND METHODS: We used electronic health record (EHR) active use data from the Oracle Cerner Advance platform capturing hourly active documentation time for 498 physicians and advance practice clinicians (eg, nurse practitioners) for 65 152 clinic days. We used k-means clustering to identify distinct daily patterns of active documentation time and analyzed the relationship between these patterns and active documentation time per note. We determined each primary care clinician's (PCC) modal documentation pattern and analyzed how consistency and deviations were related to documentation efficiency. RESULTS: We identified 8 distinct daily documentation patterns; the 3 most common patterns accounted for 80.6% of PCC-days and differed primarily in average volume of documentation time (78.1 minutes per day; 35.4 minutes per day; 144.6 minutes per day); associations with note efficiency were mixed. PCCs with >80% of days attributable to a single pattern demonstrated significantly more efficient documentation than PCCs with lower consistency; for high-consistency PCCs, days that deviated from their usual patterns were associated with less efficient documentation. DISCUSSION: We found substantial variation in efficiency across daily documentation patterns, suggesting that PCC-level factors like EHR facility and consistency may be more important than when documentation occurs. There were substantial efficiency returns to consistency, and deviations from consistent patterns were costly. CONCLUSION: Organizational leaders aiming to reduce documentation burden should pay specific attention to the ability for PCCs to execute consistent documentation patterns day-to-day.

Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics.

OBJECTIVE: This study used unsupervised machine learning (UML) cluster analysis to explore clinical phenotypes of endovascular aortic repair (EVAR) for abdominal aortic aneurysm (AAA) patients based on radiomics. METHOD: We retrospectively reviewed 1785 patients with infra-renal AAA who underwent elective EVAR procedures between January 2010 and December 2020. Pyradiomics was used to extract the radiomics features. Statistical analysis was applied to determine the radiomics features that related to severe adverse events (SAEs) after EVAR. The selected features were used for UML cluster analysis in training set and validation in test set. Comparison of basic characteristics and radiomics features of different clusters. The Kaplan-Meier analysis was conducted to generate the cumulative incidence of freedom from SAEs rate. RESULT: A total of 1180 patients were enrolled. During the follow-up, 353 patients experienced EVAR-related SAEs. In total, 1223 radiomics features were extracted from each patient, of which 23 radiomics features were finally preserved to identify different clinical phenotypes. 944 patients were allocated to the training set. Three clusters were identified in training set, in which patients had identical clinical characteristics and morphological features, while varied considerably of selected radiomics features. This encouraging performance was further approved in the test set. In addition, each cluster was well differentiated from other clusters and Kaplan-Meier analysis showed significant differences of freedom from SAEs rate between different clusters both in the training (p = .0216) and test sets (p = .0253). CONCLUSION: Based on radiomics, UML cluster analysis can identify clinical phenotypes in EVAR patients with distinct long-term outcomes.

Morphological variation and expressed sequence tags-simple sequence repeats-based genetic diversity of Aspergillus cristatus in Chinese dark tea.

Introduction: Aspergillus cristatus is a homothallic fungus that is used in the natural fermentation process of Chinese Fuzhuan tea and has been linked to the production of bioactive components. However, not much is known about the variations present in the fungus. To understand the variation of the dominant microorganism, A. cristatus, within dark tea, the present study investigated the genetic and morphological diversity of 70 A. cristatus collected across six provinces of China. Methods: Expressed sequence tags-simple sequence repeats (EST-SSR) loci for A. cristatus were identified and corresponding primers were developed. Subsequently, 15 specimens were selected for PCR amplification. Results: The phylogenetic tree obtained revealed four distinct clusters with a genetic similarity coefficient of 0.983, corresponding to previously identified morphological groups. Five strains (A1, A11, B1, D1, and JH1805) with considerable differences in EST-SSR results were selected for further physiological variation investigation. Microstructural examinations revealed no apparent differentiation among the representative strains. However, colony morphology under a range of culture media varied substantially between strains, as did the extracellular enzymatic activity (cellulase, pectinase, protease, and polyphenol oxidase); the data indicate that there are differences in physiological metabolic capacity among A. cristatus strains. Discussion: Notably, JH1805, B1, and A11 exhibited higher enzymatic activity, indicating their potential application in the production of genetically improved strains. The findings provide valuable insights into species identification, genetic diversity determination, and marker-assisted breeding strategies for A. cristatus.

How predictive of future healthcare utilisation and mortality is data-driven population segmentation based on healthcare utilisation and chronic condition comorbidity?

BACKGROUND: In recent years data-driven population segmentation using cluster analyses of mainly health care utilisation data has been used as a proxy of future health care need. Chronic conditions patterns tended to be examined after segmentation but may be useful as a segmentation variable which, in combination with utilisation could indicate severity. These could further be of practical use to target specific clinical groups including for prevention. This study aimed to assess the ability of data-driven segmentation based on health care utilisation and comorbidities to predict future outcomes: Emergency admission, A&E attendance, GP practice contacts, and mortality. METHODS: We analysed record-linked data for 412,997 patients registered with GP practices in 2018-19 in Cwm Taf Morgannwg University Health Board (CTM UHB) area within the Secure Anonymised Information Linkage (SAIL) Databank. We created 10 segments using k-means clustering based on utilisation (GP practice contacts, prescriptions, emergency and elective admissions, A&E and outpatients) and chronic condition counts for 2018 using different variable compositions to denote need. We assessed the characteristics of the segments. We employed a train/test scheme (80% training set) to compare logistic regression model predictions with observed outcomes on follow-up in 2019. We assessed the area under the ROC curve (AUC) for models with demographic variables, with and without the segments, as well as between segmentation implementations (with/without comorbidity and primary care data). RESULTS: Adding the segments to the model with demographic covariates improved the prediction for all outcomes. For emergency admissions this increased discrimination from AUC 0.65 (CI 0.64-0.65) to 0.73 (CI 0.73-0.74). Models with the segments only performed nearly as well as the full models. Excluding comorbidity showed reduced predictive ability for mortality (similar otherwise) but most pronounced reduction when excluding all primary care variables. CONCLUSIONS: This shows that the segments have satisfactory predictive ability, even for varied outcomes and a broad range of events and conditions used in the segmentation. It suggests that the segments can be a useful tool in helping to identify specific groups of need to target with anticipatory care. Identification may be refined with selected diagnoses or more specialised tools such as risk stratification.